Efficient duration and hierarchical modeling for human activity recognition
A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit both their typical duration patterns and inherent hierarchical structures. We...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier Science publishers ltd.
2009
|
| Subjects: | |
| Online Access: | http://www.elsevier.com/locate/artint http://hdl.handle.net/20.500.11937/17870 |
| _version_ | 1848749582540865536 |
|---|---|
| author | Duong, Thi Phung, Dinh Bui, Hung H. Venkatesh, Svetha |
| author_facet | Duong, Thi Phung, Dinh Bui, Hung H. Venkatesh, Svetha |
| author_sort | Duong, Thi |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit both their typical duration patterns and inherent hierarchical structures. We exploit efficient duration modeling using the novel Coxian distribution to form the Coxian hidden semi-Markov model (CxHSMM) and apply it to the problem of learning and recognizing ADLs with complex temporal dependencies.The Coxian duration model has several advantages over existing duration parameterization using multinomial or exponential family distributions, including its denseness in the space of non negative distributions, low number of parameters, computational efficiency and the existence of closed-form estimation solutions. Further we combine both hierarchical and duration extensions of the hidden Markov model (HMM) to form the novel switching hidden semi-Markov model (SHSMM), and empirically compare its performance with existing models. The model can learn what an occupant normally does during the day from unsegmented training data and then perform online activity classification, segmentation and abnormality detection. Experimental results show that Coxian modeling outperforms a range of baseline models for the task of activity segmentation. We also achieve arecognition accuracy competitive to the current state-of-the-art multinomial duration model, while gaining a significant reduction in computation. Furthermore, cross-validation model selection on the number of phases K in the Coxian indicates that only a small Kis required to achieve the optimal performance. Finally, our models are further tested in a more challenging setting in which the tracking is often lost and the activities considerably overlap. With a small amount of labels supplied during training in a partially supervised learning mode, our models are again able to deliver reliable performance, again with a small number of phases, making our proposed framework an attractive choice for activity modeling. |
| first_indexed | 2025-11-14T07:23:14Z |
| format | Journal Article |
| id | curtin-20.500.11937-17870 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:23:14Z |
| publishDate | 2009 |
| publisher | Elsevier Science publishers ltd. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-178702017-09-13T15:42:22Z Efficient duration and hierarchical modeling for human activity recognition Duong, Thi Phung, Dinh Bui, Hung H. Venkatesh, Svetha Duration modeling - Coxian - Hidden semi-Markov model - Human activity recognition - Smart surveillance A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit both their typical duration patterns and inherent hierarchical structures. We exploit efficient duration modeling using the novel Coxian distribution to form the Coxian hidden semi-Markov model (CxHSMM) and apply it to the problem of learning and recognizing ADLs with complex temporal dependencies.The Coxian duration model has several advantages over existing duration parameterization using multinomial or exponential family distributions, including its denseness in the space of non negative distributions, low number of parameters, computational efficiency and the existence of closed-form estimation solutions. Further we combine both hierarchical and duration extensions of the hidden Markov model (HMM) to form the novel switching hidden semi-Markov model (SHSMM), and empirically compare its performance with existing models. The model can learn what an occupant normally does during the day from unsegmented training data and then perform online activity classification, segmentation and abnormality detection. Experimental results show that Coxian modeling outperforms a range of baseline models for the task of activity segmentation. We also achieve arecognition accuracy competitive to the current state-of-the-art multinomial duration model, while gaining a significant reduction in computation. Furthermore, cross-validation model selection on the number of phases K in the Coxian indicates that only a small Kis required to achieve the optimal performance. Finally, our models are further tested in a more challenging setting in which the tracking is often lost and the activities considerably overlap. With a small amount of labels supplied during training in a partially supervised learning mode, our models are again able to deliver reliable performance, again with a small number of phases, making our proposed framework an attractive choice for activity modeling. 2009 Journal Article http://hdl.handle.net/20.500.11937/17870 10.1016/j.artint.2008.12.005 http://www.elsevier.com/locate/artint Elsevier Science publishers ltd. fulltext |
| spellingShingle | Duration modeling - Coxian - Hidden semi-Markov model - Human activity recognition - Smart surveillance Duong, Thi Phung, Dinh Bui, Hung H. Venkatesh, Svetha Efficient duration and hierarchical modeling for human activity recognition |
| title | Efficient duration and hierarchical modeling for human activity recognition |
| title_full | Efficient duration and hierarchical modeling for human activity recognition |
| title_fullStr | Efficient duration and hierarchical modeling for human activity recognition |
| title_full_unstemmed | Efficient duration and hierarchical modeling for human activity recognition |
| title_short | Efficient duration and hierarchical modeling for human activity recognition |
| title_sort | efficient duration and hierarchical modeling for human activity recognition |
| topic | Duration modeling - Coxian - Hidden semi-Markov model - Human activity recognition - Smart surveillance |
| url | http://www.elsevier.com/locate/artint http://hdl.handle.net/20.500.11937/17870 |